Environmental Decision-Making - New Ecoinformatics Tools in Environmental Science: Applications and Decision-making - page 221

poorly and the project is abandoned (Laudon 2011). However, correct development
methodology can mitigate these problems. There exists software capable of inter-
viewing a true expert on a subject and automatically writing the rule or knowledge
base, depending on the answers. The expert system can then be simultaneously run
before the true expert

s eyes, performing a consistency of rules check. Experts and
users can check the quality of the software before it is

'

finished.
The main mission of expert systems is to automatize and to computerize the
decision making processes in different applied areas. The applications of expert
systems

find their way into most applications. For example, Karasulu and Kor-
ukoglu (2012) applied subtraction method that uses the frame differencing in order
to develop an expert system for moving object detection. The basic idea is to
subtract the current frame from a background image and to classify each pixel either
as foreground or as background by comparing the difference with a threshold.
Therefore, the moving object is detected and tracked by using frame differencing
and by learning an updated background model. In addition, simulated annealing is
an optimization technique for soft computing in the arti cial intelligence area. This

expert system can be used for tropical cyclone tracking.
There are numerous expert systems in different practical applications of
knowledge. Such systems are used for prospecting medical diagnosis or as edu-
cational aids. Moreover, they are used in engineering and manufacture in the
control of robots, where they interrelate with vision systems. The initial attempts to
apply arti

cial intelligence to generalized problems made limited progress. How-
ever, more signi field of interest.

The period from the end of the 20th century to the beginning of the 21st century
is characterized not only by the exacerbation of the environment but also by
prognosis of negative consequences in global scale, because of anthropogenic
impacts. Particularly, this exacerbation was intensi

cant progress could be made in a restricted

ed after the Kyoto Protocol. A
settlement of arising disputes concerning the processes of the environment evolu-
tion is undoubtedly related to the ef ciency of environmental monitoring systems

synthesis, on which remote sensing technologies — both passive and active type —

depend (Krapivin et al. 2009b, 2010a, 2011).
Methodical support of remote sensing systems of land covers and radio-com-
munication stations by data about the character of screening effect of the vegetation
cover at fixed moment of the time and in the concrete geographical point, requires

the development of a technology which could reconstruct spatial images using the
episodic in the time and fragmentary in the space observations.
The environmental monitoring regime can foresee decision making situations in
real time based on the data accumulated up until the moment of the decision making
or as a result of the prior data analysis without correlation to the current time. The
statistical analysis of several events monitored by the system can be carried out by
numerous methods. The applicability of these methods is determined in each case
by a set of probabilistic parameters which characterize the phenomenon under
study. However, non-steady state and parametrical uncertainty demand a search for
new methods capable of making the decision using fragmentary time and space
data. Such methods are proposed by a sequential analysis and evolutionary